Rare events are an important limitation of discrete-eventsimulation in some areas of applications. The existing rare-eventsimulation (RES) techniques, such as importance sampling (IS),splitting, and RESTART, have been used for RES so far. However, thesetechniques not only have some limitations, but also are not general oreasy to use. In this paper, the partition of the region (PoR) methodis used as a variance reduction technique in a new RES technique forusage with a wide range of modeling and simulation languages. Threevariants of the proposed technique will be introduced: simple PoR,recursive PoR, and advanced PoR. Simple and recursive PoR methods arepowerful techniques that have some important features such as boundedrelative error; however, they are restricted to some specific models.Advanced PoR is a more general technique that integrates the PoRmethod and the IS technique. To evaluate the efficiency of theproposed technique and its variants, the comparative simulationresults of some illustrative examples using stochastic activitynetworks will be presented.
展开▼
